CN110769283B - Video pushing method and device, computer equipment and storage medium - Google Patents
Video pushing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110769283B CN110769283B CN201911051675.8A CN201911051675A CN110769283B CN 110769283 B CN110769283 B CN 110769283B CN 201911051675 A CN201911051675 A CN 201911051675A CN 110769283 B CN110769283 B CN 110769283B
- Authority
- CN
- China
- Prior art keywords
- video file
- candidate
- pushing
- candidate video
- click
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000001514 detection method Methods 0.000 claims description 18
- 238000005070 sampling Methods 0.000 claims description 9
- 238000012546 transfer Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 abstract description 14
- 230000008569 process Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 8
- 230000006399 behavior Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 208000001613 Gambling Diseases 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012353 t test Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
- H04N21/2393—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Television Signal Processing For Recording (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses a video pushing method, a video pushing device, computer equipment and a storage medium, wherein the method comprises the following steps: selecting at least part of original video files from a preset first video pool as candidate video files; pushing the candidate video file to a first client side for displaying; counting feedback operation data of the first client to the candidate video file; transferring at least part of the candidate video file to a preset second video pool according to the feedback operation data; selecting at least part of the candidate video files from the second video pool as target video files; and pushing the target video file to a second client for displaying. By probing the feedback of a small amount of first clients to the candidate video files, the candidate video files with higher quality are screened out and pushed to the second client as target video files, so that the complexity of calculation is reduced, the pushing process is simplified, the calculation cost is reduced, and the instantaneity is ensured.
Description
Technical Field
The embodiment of the invention relates to a video processing technology, in particular to a video pushing method, a video pushing device, computer equipment and a storage medium.
Background
With the rapid development of network technology, new media based on digital technology, such as live broadcast, short video, etc., are emerging continuously. Under the support of network technology, these new media often have the characteristics of innovativeness and mixed media, and videos represented by these digital media become another hot field of the network.
In order to improve the user experience, the platform providing these videos usually pushes some videos that the user is interested in to the user, so that the user can obtain more information and use the services provided by the platform.
Currently, a platform typically uses the following two methods to push video to a user:
1. push based on geographic location
In the method, the geographic position of the user is obtained in real time, and the video sent by the user around the geographic position is pushed to the user.
2. Push based on user historical behavior
The method comprises the steps of collecting historical data of videos browsed by a user, training a personalized model by using the historical data, inputting the video and characteristics of the user into the model to predict the preference degree of the user to the videos, and pushing the videos with high preference degree to the user.
However, the method of pushing based on the geographic location is limited to be capable of acquiring the geographic location of the user in real time, and the user sends a video around the geographic location, so that the application range is limited.
In addition, the mode of pushing based on the historical behaviors of the user generally adopts an off-line batch training model, so that the calculation cost is high, the model updating speed is low, and the real-time performance is poor.
Disclosure of Invention
The embodiment of the invention provides a video pushing method and device, computer equipment and a storage medium, and aims to solve the problems that the application range of pushing based on a geographic position is limited, the pushing calculation cost is high and the real-time performance is poor based on the historical behavior of a user.
In a first aspect, an embodiment of the present invention provides a video pushing method, including:
selecting at least part of original video files from a preset first video pool as candidate video files;
pushing the candidate video file to a first client side for displaying;
counting feedback operation data of the first client to the candidate video file;
transferring at least part of the candidate video file to a preset second video pool according to the feedback operation data;
selecting at least part of the candidate video files from the second video pool as target video files;
and pushing the target video file to a second client for displaying.
In a second aspect, an embodiment of the present invention further provides a video pushing apparatus, including:
the candidate video file selection module is used for selecting at least part of original video files from a preset first video pool as candidate video files;
the candidate video file pushing module is used for pushing the candidate video file to a first client side for displaying;
the feedback operation data counting module is used for counting the feedback operation data of the first client to the candidate video file;
the candidate video file transfer module is used for transferring at least part of the candidate video files to a preset second video pool according to the feedback operation data;
a target video file selection module, configured to select at least a portion of the candidate video files from the second video pool as target video files;
and the target video file pushing module is used for pushing the target video file to a second client side for displaying.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the video push method of the first aspect.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the video push method according to the first aspect.
In this embodiment, at least a part of original video files are selected from a preset first video pool as candidate video files, the candidate video files are pushed to a first client for displaying, feedback operation data of the first client to the candidate video files are counted, at least part of the candidate video files are transferred to a preset second video pool according to the feedback operation data, at least part of candidate video files are selected from the second video pool as target video files, the target video files are pushed to the second client side for displaying, and compared with a pushing mode based on geographic positions, the video files pushed by the embodiment are not limited by regions, the video files in the video pool can be directly pushed to the user, so that the geographic position of the user does not need to be acquired, and the user around the geographic position does not need to send the video, thereby greatly improving the application range; compared with a pushing mode based on the historical behaviors of the user, the method and the device have the advantages that the candidate video file with high quality is screened out by probing the feedback of a small number of first clients to the candidate video file and is pushed to the second client as the target video file, the historical data of the user does not need to be collected to train the personalized model, the calculation complexity is reduced, the pushing process is simplified, the calculation cost is reduced, and the instantaneity is guaranteed.
Drawings
Fig. 1 is a flowchart of a video push method according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an example of a video pool provided by an embodiment of the present invention;
fig. 3 is a flowchart of a video pushing method according to a second embodiment of the present invention;
fig. 4 is a flowchart of a video pushing method according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a video pushing apparatus according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer device according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
Example one
Fig. 1 is a flowchart of a video pushing method according to an embodiment of the present invention, where this embodiment is applicable to a situation where a small amount of user feedback is detected through a video file and then a full amount of users are pushed, and the method may be executed by a video pushing apparatus, where the video pushing apparatus may be implemented by software and/or hardware and may be configured in a computer device, for example, the method specifically includes the following steps:
s101, selecting at least a part of original video files from a preset first video pool as candidate video files.
An original video file belongs to a video (video) and comprises a plurality of frames of continuous image data, and when the continuous image data changes by more than 24 frames per second, human eyes cannot distinguish a single static picture according to the persistence of vision principle and the original video file looks like a smooth continuous visual effect.
In this embodiment, the video file may be obtained in advance as a sample of the training content audit model, which is called a sample video file, by capturing the video file from a network, accumulating the video file uploaded by the user, downloading the video file from an open database, and the like.
The format and form of the original video file are different for different service scenarios, which is not limited in this embodiment.
Further, the format of the Video file may include MPEG (Moving Picture Experts Group), RMVB (Variable bit rate), AVI (Audio Video Interleaved), FLV (Flash Video, streaming media format), and the like.
The format of the original video file may include short videos, live videos, movies, television shows, and the like.
In the present embodiment, as shown in fig. 2, a first video pool 201 and a second video pool 202 are constructed in advance on a computer device.
The first video pool 201 may refer to an area storing original video files, such as a database, a buffer queue, and the like.
The second video pool 202 may refer to an area, such as a database, a cache queue, etc., where candidate video files are stored.
It should be noted that, in the first video pool 201, summary information of the original video file, such as a document description, a cover page, an address, etc., is stored, but the original video file itself is not necessarily stored.
Similarly, summary information of the candidate video file, such as a document description, a cover page, an address, etc., is stored in the second video pool 202, but the candidate video file itself is not necessarily stored.
The file description can be initialized by using the description of the video file, and operators can reconfigure the corresponding file description after watching the video file; the cover adopts an automatic interception algorithm to intercept image data for initialization, and operators can select proper image data as the video cover after watching the video file.
In addition, the original video file stored in the first video pool 201 may be an originally acquired video file, or may also be a video file recalled when the originally acquired video file meets a certain condition (for example, the time length exceeds a preset threshold, the resolution exceeds a preset threshold, and the like), which is not limited in this embodiment.
In a specific implementation, at least a portion of the original video files may be selected from the first video pool as candidate video files to be pushed to the user 203.
S102, the candidate video file is pushed to a first client side to be displayed.
In a specific implementation, if the first client meets a preset condition, such as pausing playing a video, entering a live broadcast room, and the like, the computer device may push (push) the candidate video file to a small number of first clients, and the first clients display the candidate video file for the user to browse.
The pushing of the candidate video file to the first client means that the summary information of the candidate video file is pushed to the first client, and does not necessarily mean that the candidate video file itself is pushed to the first client.
When the first client displays the summary information of the candidate video file, if the first client receives a click operation, the candidate video file is loaded to be played.
It should be noted that, if the first client is configured with a computer device, for example, the computer device is a server of a short video platform, and the first client is a short video application, the pushed candidate video file may be regarded as information for guessing user preferences.
If the first client is a non-matching computer device, for example, the computer device is a server of a short video platform and the first client is a browser, the pushed candidate video file may be regarded as an advertisement.
In a push mode, the region information and the language information may be set in advance for the candidate video file, and the region information and the language information may be set for the user.
These users can be buffered in the queue, and at a certain time interval, the users are added and the users in the queue are updated.
The region information is used to indicate regions such as countries, regions, etc., such as china, singapore, korea, etc.
The language information is used to represent languages such as Chinese, English, Portuguese, etc.
In the push mode, on one hand, the region information and the language information set for the candidate video file are determined, and on the other hand, the first user identification marking the region information and the language information is searched.
The first user identifier may indicate information for identifying a user, such as a user account, a user ID, and an Equipment identifier (e.g., an International Mobile Equipment Identity (IMEI)), and the like.
And pushing the candidate video file to a first client marked with a first user identifier for displaying.
In addition, for different attributes (such as regions and languages) of the candidate video files, corresponding detection time and detection number may be set for the candidate video files in advance, and based on the detection time and the detection number, after selecting the candidate video files, on one hand, the detection time and the detection number set for the candidate video files are determined, and on the other hand, the number of the pushed candidate video files is counted as the pushing number.
The probe number is compared to the push number.
And if the pushing quantity is less than or equal to the detection quantity, pushing the candidate video file to the first client for display when the detection time is reached.
And if the pushing quantity is larger than the detecting quantity, forbidding to push the candidate video file to the first client side for displaying.
S103, counting feedback operation data of the first client to the candidate video file.
As shown in fig. 2, in the process of browsing the candidate video file by the user 203, the user 203 may perform operations of clicking, sharing, deleting, and the like on the candidate video file for feedback, so that a reaction of the user to the candidate video file stored in the first video pool 201 may be explored.
The computer device receives the operation sent by the first client and aiming at the candidate video file, and accordingly feedback operation data are generated.
Further, the feedback operation data may include operation data indicating positive feedback, such as clicking a candidate video file, sharing a link of the candidate video file, and the like, and may also include operation data indicating negative feedback, such as deleting the candidate video file, and the like.
And S104, transferring at least part of the candidate video file to a preset second video pool according to the feedback operation data.
In a specific implementation, as shown in fig. 2, candidate video files stored in the first video pool 201 are pushed to a small number of users 203 for probing, and feedback operation data thereof is collected, which may indicate the quality of the candidate video files relative to the users 203 to some extent, so that candidate video files with higher quality are transferred to the second video pool 202.
And S105, selecting at least part of the candidate video files from the second video pool as target video files.
In a specific implementation, as shown in fig. 2, at least a part of candidate video files may be selected from the second video pool 202 as target video files to be pushed to the user 203.
It should be noted that the number of users who push the candidate video file is small, while the number of users who push the target video file is large, and the number of users who push the target video file is generally much larger than that of the first clients.
And S106, pushing the target video file to a second client for displaying.
In a specific implementation, if the second client meets a preset condition, such as pausing playing a video, entering a live broadcast room, and the like, the computer device may push (push) the target video file to the full second client, and the second client displays the target video file for the user to browse.
The pushing of the target video file to the second client means that the summary information of the target video file is pushed to the second client, and does not necessarily mean that the target video file itself is pushed to the second client.
And when the second client displays the summary information of the target video file, if the second client receives the click operation, the second client loads the target video file for playing.
It should be noted that, if the second client is configured with a computer device, for example, the computer device is a server of a short video platform, and the second client is a short video application, the pushed candidate video file may be regarded as information for guessing the user preference.
If the second client is a non-supporting computer device, for example, the computer device is a server of a short video platform, and the second client is a browser, the pushed target video file may be regarded as an advertisement.
Generally, for the same video file (candidate video file, target video file), the first client and the second client have the same attribute, which ensures that the tested effect of the video file can be continued to the normal push.
In a push method, region information and language information may be set in advance for a target video file, and region information and language information may be set for a user.
These users can be buffered in the queue, and at a certain time interval, the users are added and the users in the queue are updated.
The region information is used to indicate regions such as countries, regions, etc., such as china, singapore, korea, etc.
The language information is used to represent languages such as Chinese, English, Portuguese, etc.
In the push mode, on one hand, the region information and the language information set for the target video file are determined, and on the other hand, a second user identifier for marking the region information and the language information is searched.
The first user identifier may indicate information for identifying the user, such as a user account, a user ID, an equipment identifier (e.g., an IMEI code), and the like.
And pushing the target video file to a second client marked with a second user identifier for displaying.
In addition, for the same video file (candidate video file, target video file), if the video file is previously pushed to a certain user as a candidate video file, the video file is taken as a target video file, so that the duplicate removal processing can be performed on the user, the situation that the same video file is repeatedly pushed to the same user is avoided, and the user experience is ensured.
In this embodiment, at least a part of original video files are selected from a preset first video pool as candidate video files, the candidate video files are pushed to a first client for displaying, feedback operation data of the first client to the candidate video files are counted, at least part of the candidate video files are transferred to a preset second video pool according to the feedback operation data, at least part of candidate video files are selected from the second video pool as target video files, the target video files are pushed to the second client side for displaying, and compared with a pushing mode based on geographic positions, the video files pushed by the embodiment are not limited by regions, the video files in the video pool can be directly pushed to the user, so that the geographic position of the user does not need to be acquired, and the user around the geographic position does not need to send the video, thereby greatly improving the application range; compared with a pushing mode based on the historical behaviors of the user, the method and the device have the advantages that the candidate video file with high quality is screened out by probing the feedback of a small number of first clients to the candidate video file and is pushed to the second client as the target video file, the historical data of the user does not need to be collected to train the personalized model, the calculation complexity is reduced, the pushing process is simplified, the calculation cost is reduced, and the instantaneity is guaranteed.
Example two
Fig. 3 is a flowchart of a video pushing method according to a second embodiment of the present invention, which is based on the foregoing embodiment and further adds a processing operation for selecting a candidate video file based on Thompson Sampling (Thompson Sampling).
As shown in FIG. 2, in the course of heuristics user responses, heuristics may be modeled in order to quickly try out high click-through rate candidate video files from a first video pool 201 to join a second video pool 202.
Assuming that the number of users in a single trial is N, the number of times of presentation of each trial is limited to M, and at least the number of times of trial is K, if the number of pushes exceeds K and the number of times of presentation exceeds M, it can be considered that the click rate of the trial has converged, and the deviations caused by different users and different sending times can be eliminated, then the number of pushes in a single trial is:
each user selecting one of the n candidate video files for a heuristic belongs to the classic Bernoulli Multi-arm gambling machine problem (Bernoulli Multi-arm Bandit), and if the user clicks on a tentative candidate video file, a forward score is calculated, and the goal of the model is to maximize the cumulative benefit of the heuristic, within the limit of a finite number of heuristics M.
Reducing the heuristic problem to a Markov decision Process (Markov decision Process) with no states, denoted as<A,R>And selecting one candidate video file from the n candidate video files for trial, wherein the click rate of the n candidate video files is expressed as theta1,θ2,...θn}。
A represents a set of actions, each action representing a user selecting one of the n candidate video files to be explored. In the selection action, the predicted gain after the trial for selecting the candidate video file is calculated and expressed as Q (a) ═ E [ r | a]θ. If the ith candidate video file is selected in the tth heuristic, then the predicted gain of the tth heuristic is Q (a)t)=θi. R represents a feedback function, and the real feedback value R in the t test processt=R(at) With Q (a)t) The probability of (2) is 1.
The goal of the model is to maximize the cumulative revenueThe yield of the corresponding candidate video file of the optimal selection mode under the ideal condition is as follows:
thus, the loss function is a loss value that does not select the optimal candidate video file:
wherein the loss function is used to compare against the gain.
In this embodiment, Thompson Sampling (Thompson Sampling) is used for solving, and it is assumed that q (a) satisfies Beta distribution (Beta distribution) and click rate θ satisfies Bernoulli distribution (Bernoulli distribution). Beta (α, β) ranges from [0,1], where α, β are the number of clicks and no clicks, respectively.
The policy for each selection of a candidate video file may be expressed as:
the above formula shows which candidate video file of the first n candidate video files is selected for trial at time t.
a represents the selected candidate video file, a belongs to A, and A represents the collection of the first n candidate video files.
htAnd the state of the t moment is represented, and the state comprises the beta distribution of the current n candidate video files.
π(a|ht) Denotes the time h at ttIn the state, the probability of a is selected.
Q (a) is the same as above, and represents the benefit of the selection a.
Denotes the time h at ttIn this state, the probability of earning a is greater than the probability of earning all other candidate video files.
atCandidate video file representing the t-th selection, 1 (a)t=argmaxa∈AQ (a)) indicates that if the candidate video file selected for the t-th time is the most profitable candidate video file, 1 is returned, otherwise 0 is returned.
Beta (alpha) corresponding to each candidate video file every time the candidate video file is selectedi,βi) Respectively sampling the distribution to obtain Q (a), wherein a belongs to A, selecting a candidate video file corresponding to the maximum value for probing, and the candidate video file is represented as at=argmaxa∈AQ(a)。
And after the feedback operation data of the user reflows, updating the beta distribution of each candidate video file:
αi←αi+rt1(at=ai)
βi=βi+(1-rt)1(at=ai)
wherein, 1 (a)t=ai) Represents an indicator function ift=ai1 is returned, otherwise 0 is returned.
Referring to fig. 3, the method specifically includes the following steps:
s301, selecting an original video file in a preset first video pool.
In this embodiment, a plurality of original video files are stored in the first video pool, and the original video files are configured with click rates.
The click rate may refer to a probability that the user clicks the candidate video file when the original video file is pushed to the first client as the candidate video file.
Because the number of the original video files is large, the original video files can be selected in a random mode, a sequencing mode and the like, and whether the original video files can be pushed as candidate video files or not is judged.
In one alternative, the original video file may be searched in a preset first video pool, and at least a portion of the original video file may be selected based on a click-through rate of the original video file.
For example, in order to quickly screen out candidate video files with high click rate, the top n items of the candidate video files with high click rate can be intercepted, that is, the click rate is sorted in a reverse order, the higher the sorting is, the higher the click rate is, and conversely, the lower the sorting is, the lower the click rate is.
And selecting the original video files to which the n highest click rates belong, wherein n is a positive integer and belongs to adjustable parameters.
S302, generating probability distribution for the click rate of the original video file.
In a specific implementation, the click rate of the original video file belongs to the probability, and the probability of the probability is calculated, so that the probability distribution of the click rate can be obtained.
In one example of a probability distribution, the probability distribution includes a Beta distribution, the domain of which is [0,1], i.e., the Beta distribution describes a probability distribution that defines random variables over the interval [0,1], determined by two parameters α > 0 and β > 0, commonly denoted μ β (μ | α, β).
In practical use, a Beta distribution is usually taken as a probability distribution, and the Beta distribution describes a univariate distribution, so that the Beta distribution can be taken as a prior probability of a binomial distribution.
Further, the original video file is configured with a presentation number.
At the beginning, in a preset region, such as the kth country, the average value of the click rate of the candidate video files is calculated to serve as the average click rate, and the initial click rate of the original video file is calculated based on the average click rate.
For example, the initial click rate of the original video file may be obtained by multiplying the average click rate by a specified coefficient, wherein the coefficient is greater than 1, such as 2.
Because the newly configured original video file is not displayed and clicked, the display quantity and the click rate are initialized, and particularly the initial click rate is improved, so that the newly configured original video file initially obtains a chance of being preferentially used as a candidate video file to be pushed.
In addition, in a preset region, such as the kth country, the minimum value of the display number of the candidate video files is calculated to serve as the lowest display number, and the initial display number of the original video files is calculated based on the lowest display number.
For example, the lowest number of presentations is directly assigned to the initial number of presentations of the original video file.
In this example, the product between the click rate of the original video file and the number of presentations of the original video file may be calculated as the number of times the original video file was clicked.
Calculating the non-click rate of the original video file based on the click rate of the original video file, namely 1-the click rate of the original video file, namely the non-click rate of the original video file.
And calculating the product of the un-clicked rate of the original video file and the display number of the original video file as the number of times that the original video file is not clicked.
And generating beta distribution for the click rate of the original video file by taking the clicked times as alpha and the unchecked times as beta.
Assuming average click rate of CkThe lowest number of presentations is DkIn the case of beta distribution:
α=Dk×2Ck
β=Dk×(1-2Ck)
s303, sampling the probability value which accords with the probability distribution, and taking the probability value as the expected click rate of the original video file.
A random value is generated through the probability distribution, and a click rate which accords with the probability distribution can be obtained and used as an expected click rate of the original video file.
S304, selecting at least part of the original video files as candidate video files based on the expected click rate.
For n original video files, n expected click rates can be known, and a proper original video file is selected as a candidate video file.
In general, the original video file that is expected to have the highest click through rate may be selected as the candidate video file.
Of course, the original video file with the expected click rate being the second highest or the third highest may also be selected as the candidate video file, which is not limited in this embodiment.
S305, pushing the candidate video file to a first client side for displaying.
S306, counting the number of times that the candidate video file is clicked in the first client as the number of clicks.
S307, counting the number of the candidate video files displayed in the first client as the display number.
S308, calculating the click rate of the candidate video file based on the click number and the display number.
In this embodiment, the feedback operation data includes the number of presentations and the click rate.
After the operation of the user is performed with a reflow, on one hand, the number of times that the candidate video file is clicked in the first client is counted as the number of clicks, and on the other hand, the number of the candidate video files displayed in the first client is counted as the number of displays.
It should be noted that the click number refers to the total number after accumulating the number clicked at this time of pushing, and the presentation number refers to the total number after accumulating the number presented at this time of pushing.
And calculating the click rate of the candidate video files based on the click number and the display number, wherein the probability distribution is updated correspondingly.
In general, the ratio of the number of clicks to the number of presentations may be calculated as the click rate of the candidate video file.
In order to enable the initial click rate to be in a nonsensical condition such as 0 and the like and enable the initial click rate confidence coefficient to be low, the ratio of the number of clicks to the number of displays can be calculated, the smoothing factor is used for adjusting the ratio to obtain the click rate of the candidate video file, the click rate is trimmed through the smoothing factor, the nonsensical condition such as the click rate being 0 is avoided, the influence of the click rate with the low initial confidence coefficient is reduced, the click rate can be smoothed, and the click rate is prevented from being too large in fluctuation.
The smoothing factors are all constants and can be set according to the number of users trying for different regions.
In one example, the click rate is click number/show number + smooth click number/(show number + smooth show number), where the smooth click number and the smooth show number are smoothing factors.
S309, if the display number of the candidate video files exceeds a preset number threshold, transferring the candidate video files to a preset second video pool.
In this embodiment, a number threshold may be preset, and the number of presentations of the candidate video file may be compared with the number threshold.
And if the display quantity of the candidate video files exceeds a quantity threshold value, transferring the candidate video files to a second video pool.
In addition, if the click rate of the candidate video file does not exceed the preset click rate threshold, the candidate video file is prohibited from being pushed to the first client.
S310, candidate video files are searched in the second video pool.
S311, selecting at least part of the candidate video files as target video files based on the click rate.
In this embodiment, the candidate video files in the second video pool are configured with a click through rate, and an appropriate candidate video file can be selected as the target video file through the click through rate.
In order to quickly screen out a target video file with a high click rate, the first m pieces of the target video file with the high click rate can be intercepted, namely, the click rate is sorted in a reverse order, the higher the sorting is, the higher the click rate is, and otherwise, the lower the sorting is, the lower the click rate is.
And selecting the candidate video files to which the m highest click rates belong as target video files, wherein m is a positive integer and belongs to adjustable parameters.
It should be noted that after the target video file is pushed to the second client for display, the click rate of the target video file may be updated according to the operation of the second client on the target video file.
S312, pushing the target video file to a second client side for displaying.
In the embodiment, an original video file is selected from a preset first video pool, probability distribution is generated for the click rate of the original video file, the probability value which accords with the probability distribution is sampled to serve as the expected click rate of the original video file, at least part of the original video file is selected based on the expected click rate to serve as a candidate video file, and the probability distribution of the click rate is sampled, so that the calculation speed is high, the candidate video file with high quality can be quickly filtered, the interest of a user can be positioned in real time, and the integral click rate of the user is improved.
EXAMPLE III
Fig. 4 is a flowchart of a video push method according to a third embodiment of the present invention, where the present embodiment further pushes processing operations of monitoring based on the foregoing embodiment, and the method specifically includes the following steps:
s401, selecting at least a part of original video files from a preset first video pool as candidate video files.
S402, pushing the candidate video file to a first client side for displaying.
S403, counting a first pushing index for pushing the candidate video file in a first time period.
S404, determining a second time period relative to the first time period.
S405, acquiring a second pushing index for pushing the candidate video file in the second time period.
S406, if the difference value between the first pushing index and the second pushing index is larger than a preset index threshold value, alarm information is generated.
In this embodiment, candidate video files pushed within a period of time may be monitored, and if a significant difference is found, alarm information is generated and sent to a corresponding operator.
Further, in one aspect, first push indexes, such as the number of pushes, the number of shows, the number of clicks, and the like, for pushing the candidate video file in the first time period are counted.
On the other hand, a second time period which can be compared with the first time period is determined, and first pushing indexes, such as the pushing quantity, the showing quantity, the clicking quantity and the like, of the candidate video files pushed in the first time period are counted.
In one case, the second time period is a time period belonging to a different cycle and being at the same position, and the same ratio is realized.
In this case, a first period (e.g., days) at which the first time period (e.g., hours) is located is determined, and an interval at which the first time period is located at the first period is determined.
A second period (e.g., days) preceding the first period is determined, and a period in the second period that is in the interval is set as a second period (e.g., hours).
In another case, the second time period is of the same period, at a different location, than the first time period, achieving a ring ratio.
In this case, a period (e.g., day) in which the first period (e.g., hour) is located is determined, and in this period, a period located before the first period is set as the second period (e.g., hour).
And comparing the first push index in the first time period with the second push index in the second time period, and if the difference value between the first push index and the second push index is greater than a preset index threshold value, determining that a significant difference occurs.
It should be noted that, the candidate video file referred to in this embodiment may refer to any one of the candidate video files pushed to the first client in the first time period and the second time period, and does not refer to a specific candidate video file.
And S407, counting feedback operation data of the first client to the candidate video file.
And S408, transferring at least part of the candidate video file to a preset second video pool according to the feedback operation data.
And S409, selecting at least part of the candidate video files from the second video pool as target video files.
S410, pushing the target video file to a second client side for displaying.
In this embodiment, a first push index for pushing a candidate video file in a first time period is counted, a second time period opposite to the first time period is determined, a second push index for pushing the candidate video file in the second time period is obtained, if a difference value between the first push index and the second push index is greater than a preset index threshold value, alarm information is generated, an alarm is given when a significant difference is monitored, and the pushing safety is ensured.
Example four
Fig. 5 is a schematic structural diagram of a video pushing apparatus according to a fourth embodiment of the present invention, where the apparatus may specifically include the following modules:
a candidate video file selecting module 501, configured to select at least part of an original video file from a preset first video pool as a candidate video file;
a candidate video file pushing module 502, configured to push the candidate video file to a first client for display;
a feedback operation data statistics module 503, configured to count feedback operation data of the first client to the candidate video file;
a candidate video file transfer module 504, configured to transfer at least part of the candidate video file to a preset second video pool according to the feedback operation data;
a target video file selecting module 505, configured to select at least a part of the candidate video files from the second video pool as target video files;
and a target video file pushing module 506, configured to push the target video file to a second client for display.
In one embodiment of the present invention, the candidate video file selection module 501 includes:
the original video file selection submodule is used for selecting an original video file in a preset first video pool, and the original video file is configured with a click rate;
the probability distribution generation submodule is used for generating probability distribution for the click rate of the original video file;
a probability value sampling submodule for sampling a probability value according with the probability distribution as an expected click rate of the original video file;
and the expected click rate selection sub-module is used for selecting at least part of the original video files as candidate video files based on the expected click rate.
In an embodiment of the present invention, the original video file selection sub-module includes:
the device comprises an original video file searching unit, a first video searching unit and a second video searching unit, wherein the original video file searching unit is used for searching an original video file in a preset first video pool, and the original video file is configured with a click rate;
and the click rate selection unit is used for selecting at least part of the original video file based on the click rate.
In one embodiment of the present invention, the click rate selecting unit includes:
the click rate sorting subunit is used for sorting the click rates in a reverse order;
and the sorting selection subunit is used for selecting the original video files to which the n highest-sorting click rates belong.
In one embodiment of the present invention, the original video file is configured with a display number, and the probability distribution includes a beta distribution;
the probability distribution generation submodule includes:
the click frequency generation unit is used for calculating the product of the click rate of the original video file and the display number of the original video file as the clicked frequency of the original video file;
the non-click rate calculating unit is used for calculating the non-click rate of the original video file based on the click rate of the original video file;
the non-click frequency generation unit is used for calculating the product of the non-click rate of the original video file and the display number of the original video file as the non-click frequency of the original video file;
and the beta distribution generating unit is used for generating the beta distribution for the click rate of the original video file by taking the clicked times as alpha and the non-clicked times as beta.
In an embodiment of the present invention, the candidate video file selection module 501 further includes:
the average click rate calculation submodule is used for calculating the average value of the click rates of the candidate video files in a preset region to serve as the average click rate;
the click rate initialization submodule is used for calculating the initial click rate of the original video file based on the average click rate;
or,
the minimum display number calculation submodule is used for calculating the minimum value of the display number of the candidate video files in a preset region to serve as the minimum display number;
and the display quantity initialization submodule is used for calculating the initial display quantity of the original video file based on the lowest display quantity.
In one embodiment of the present invention, the click-through rate initialization sub-module comprises:
and the coefficient product unit is used for multiplying the average click rate by a specified coefficient to obtain the initial click rate of the original video file, wherein the coefficient is more than 1.
In one embodiment of the present invention, the candidate video file pushing module 502 comprises:
the first video attribute determining submodule is used for determining the region information and the language information set for the candidate video file;
the first user identifier searching submodule is used for searching a first user identifier for marking the region information and the language information;
the first mark pushing submodule is used for pushing the candidate video file to a first client side marked with the first user identification for displaying;
the target video file pushing module 506 includes:
the second video attribute determining submodule is used for determining the region information and the language information set for the target video file;
the second user identification searching submodule is used for searching a second user identification for marking the region information and the language information;
and the second mark pushing submodule is used for pushing the target video file to a second client marked with the second user identifier for displaying.
In one embodiment of the present invention, the candidate video file pushing module 502 comprises:
the detection parameter determining submodule is used for determining the detection time and the detection quantity set for the candidate video file;
a pushed number counting submodule for counting the number of the candidate video files which have been pushed as a pushed number;
the video pushing sub-module is used for pushing the candidate video file to a first client for display when the detection time is up if the pushing quantity is smaller than or equal to the detection quantity;
and the pushing prohibition submodule is used for prohibiting the candidate video files from being pushed to the first client side for displaying if the pushing quantity is greater than the detection quantity.
In one embodiment of the invention, the feedback operation data comprises display quantity and click rate;
the feedback operation data statistics module 503 includes:
the click number counting submodule is used for counting the number of times that the candidate video file is clicked in the first client as the click number;
a display quantity counting submodule, configured to count the number of the candidate video files displayed in the first client as a display quantity;
and the click rate calculation submodule is used for calculating the click rate of the candidate video file based on the click number and the display number.
In one embodiment of the present invention, the click rate calculation sub-module includes:
the ratio calculation unit is used for calculating the ratio between the number of clicks and the number of displays;
and the ratio adjusting unit is used for adjusting the ratio by using a smoothing factor to obtain the click rate of the candidate video file.
In one embodiment of the present invention, the feedback operation data includes click rate;
the candidate video file transfer module 504 includes:
and the condition transfer submodule is used for transferring the candidate video files to a preset second video pool if the display quantity of the candidate video files exceeds a preset quantity threshold value.
In one embodiment of the present invention, further comprising:
and the pushing prohibition module is used for prohibiting the candidate video file from being pushed to the first client side if the click rate of the candidate video file does not exceed a preset click rate threshold value.
In one embodiment of the present invention, the target video file selection module 505 comprises:
a candidate video file searching submodule, configured to search for a candidate video file in the second video pool, where the candidate video file is configured with a click rate;
and the click rate selection submodule is used for selecting at least part of the candidate video files as target video files based on the click rate.
In one embodiment of the present invention, the click rate selection sub-module comprises:
the reverse ordering unit is used for performing reverse ordering on the click rate;
and the attribution selection unit is used for selecting the candidate video file to which the m highest click rates belong as the target video file.
In one embodiment of the present invention, further comprising:
the first pushing index counting module is used for counting a first pushing index for pushing the candidate video file in a first time period;
a time period determination module for determining a second time period relative to the first time period;
the second pushing index counting module is used for acquiring a second pushing index for pushing the candidate video file in the second time period;
and the alarm information generation module is used for generating alarm information if the difference value between the first pushing index and the second pushing index is greater than a preset index threshold value.
In one embodiment of the present invention, the time period determination module includes:
the first period determining submodule is used for determining a first period in which the first time period is positioned;
the interval determining submodule is used for determining the interval of the first time period in the first period;
a second period determining submodule for determining a second period located before the first period;
the interval setting submodule is used for setting the period in the interval in the second period as a second time period;
or,
the period determining submodule is used for determining the period of the first time period;
and the time period setting submodule is used for setting the time period before the first time period as a second time period in the period.
The video pushing device provided by the embodiment of the invention can execute the video pushing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 6 is a schematic structural diagram of a computer device according to a fifth embodiment of the present invention. As shown in fig. 6, the computer apparatus includes a processor 600, a memory 601, a communication module 602, an input device 603, and an output device 604; the number of processors 600 in the computer device may be one or more, and one processor 600 is taken as an example in fig. 6; the processor 600, the memory 601, the communication module 602, the input device 603 and the output device 604 in the computer apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 6.
The memory 601 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as modules corresponding to the connection method in the present embodiment (for example, a candidate video file selection module 501, a candidate video file push module 502, a feedback operation data statistics module 503, a candidate video file transfer module 504, a target video file selection module 505, and a target video file push module 506 in the video push apparatus shown in fig. 5). The processor 600 executes various functional applications and data processing of the computer device by executing software programs, instructions and modules stored in the memory 601, that is, implements the video push method described above.
The memory 601 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the computer device, and the like. Further, the memory 601 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 601 may further include memory located remotely from processor 600, which may be connected to a computer device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
And the communication module 602 is configured to establish a connection with the display screen and implement data interaction with the display screen. The input device 603 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the computer apparatus.
The computer device provided in this embodiment may perform the video pushing method provided in any embodiment of the present invention, and its corresponding functions and advantages are described in detail.
EXAMPLE six
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a video push method, and the method includes:
selecting at least part of original video files from a preset first video pool as candidate video files;
pushing the candidate video file to a first client side for displaying;
counting feedback operation data of the first client to the candidate video file;
transferring at least part of the candidate video file to a preset second video pool according to the feedback operation data;
selecting at least part of the candidate video files from the second video pool as target video files;
and pushing the target video file to a second client for displaying.
Of course, the computer program of the computer-readable storage medium provided by the embodiment of the present invention is not limited to the method operations described above, and may also perform related operations in the video push method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the video pushing apparatus, the units and modules included in the embodiment are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (18)
1. A video push method, comprising:
selecting at least part of original video files from a preset first video pool as candidate video files;
pushing the candidate video file to a first client side for displaying;
counting a first pushing index for pushing the candidate video file in a first time period;
determining a second time period relative to the first time period;
acquiring a second pushing index for pushing the candidate video file in the second time period;
if the difference value between the first pushing index and the second pushing index is larger than a preset index threshold value, generating alarm information;
the determining a second time period relative to the first time period comprises:
determining a first period in which the first time period is located;
determining an interval in which the first period of time is located at the first cycle;
determining a second period located before the first period;
setting a cycle in the second cycle that is in an interval as a second period of time;
or determining the period of the first time period;
setting a time period before the first time period as a second time period in the cycle;
counting feedback operation data of the first client to the candidate video file;
transferring at least part of the candidate video file to a preset second video pool according to the feedback operation data;
selecting at least part of the candidate video files from the second video pool as target video files;
and pushing the target video file to a second client for displaying.
2. The method according to claim 1, wherein the selecting at least a portion of the original video file from the preset first video pool as the candidate video file comprises:
selecting an original video file in a preset first video pool, wherein the original video file is configured with a click rate;
generating probability distribution for the click rate of the original video file;
sampling a probability value which accords with the probability distribution to serve as an expected click rate of the original video file;
selecting at least a portion of the original video file as a candidate video file based on the desired click through rate.
3. The method of claim 2, wherein selecting the original video file in the preset first video pool comprises:
searching an original video file in a preset first video pool, wherein the original video file is configured with a click rate;
selecting at least a portion of the original video file based on the click through rate.
4. The method of claim 3, wherein selecting at least a portion of an original video file based on the click-through rate comprises:
sorting the click rates in a reverse order;
and selecting the original video files to which the n highest click rates belong.
5. The method of claim 2, wherein the original video file is configured with a number of shows, and wherein the probability distribution comprises a beta distribution;
generating a probability distribution for the click rate of the original video file, including:
calculating the product of the click rate of the original video file and the display number of the original video file as the number of times of clicking the original video file;
calculating the non-click rate of the original video file based on the click rate of the original video file;
calculating the product of the un-clicked rate of the original video file and the display number of the original video file as the number of times that the original video file is not clicked;
and generating beta distribution for the click rate of the original video file by taking the clicked times as alpha and the unchecked times as beta.
6. The method according to any one of claims 2-5, wherein selecting at least a portion of the original video file from a preset first video pool as the candidate video file further comprises:
calculating the average value of the click rate of the candidate video files in a preset region to serve as the average click rate;
calculating the initial click rate of the original video file based on the average click rate;
or,
in a preset region, calculating the minimum value of the display number of the candidate video files as the lowest display number;
and calculating the initial display number of the original video file based on the minimum display number.
7. The method of claim 6, wherein calculating an initial click-through rate of an original video file based on the average click-through rate comprises:
and multiplying the average click rate by a specified coefficient to obtain the initial click rate of the original video file, wherein the coefficient is more than 1.
8. The method according to any one of claims 1 to 5,
the pushing the candidate video file to a first client for displaying comprises:
determining region information and language information set for the candidate video file;
searching a first user identification for marking the region information and the language information;
pushing the candidate video file to a first client marked with the first user identifier for displaying;
the pushing the target video file to a second client for displaying comprises:
determining region information and language information set for the target video file;
searching a second user identification for marking the region information and the language information;
and pushing the target video file to a second client marked with the second user identifier for displaying.
9. The method according to any one of claims 1-5, wherein said pushing the candidate video file to the first client for presentation comprises:
determining the detection time and the detection number set for the candidate video files;
counting the number of the candidate video files which are pushed as the pushing number;
if the pushing quantity is smaller than or equal to the detection quantity, pushing the candidate video file to a first client side for display when the detection time is reached;
and if the pushing quantity is larger than the detecting quantity, forbidding to push the candidate video file to the first client side for displaying.
10. The method according to any one of claims 1-5, wherein the feedback operation data includes presentation number, click-through rate;
the counting feedback operation data of the first client to the candidate video file comprises:
counting the number of times that the candidate video file is clicked in the first client as the number of clicks;
counting the number of the candidate video files displayed in the first client as the display number;
and calculating the click rate of the candidate video file based on the click number and the display number.
11. The method of claim 10, wherein calculating the click rate of the candidate video file based on the number of clicks and the number of impressions comprises:
calculating the ratio of the number of clicks to the number of displays;
and adjusting the ratio by using a smoothing factor to obtain the click rate of the candidate video file.
12. The method of claim 10, wherein the step of determining the target position is performed by a computer
The transferring at least part of the candidate video file to a preset second video pool according to the feedback operation data comprises:
and if the display quantity of the candidate video files exceeds a preset quantity threshold value, transferring the candidate video files to a preset second video pool.
13. The method of claim 10, further comprising:
and if the click rate of the candidate video file does not exceed a preset click rate threshold value, the candidate video file is prohibited from being pushed to the first client.
14. The method according to any one of claims 1-5, wherein said selecting at least a portion of said candidate video file from said second video pool as a target video file comprises:
searching candidate video files in the second video pool, wherein the candidate video files are configured with click rates;
selecting at least a portion of the candidate video files as target video files based on the click through rate.
15. The method of claim 14, wherein selecting at least a portion of the candidate video files as target video files based on the click-through rate comprises:
sorting the click rates in a reverse order;
and selecting the candidate video file to which the m highest click rates belong as a target video file.
16. A video push apparatus, comprising:
the candidate video file selection module is used for selecting at least part of original video files from a preset first video pool as candidate video files;
the candidate video file pushing module is used for pushing the candidate video file to a first client side for displaying;
the first pushing index counting module is used for counting a first pushing index for pushing the candidate video file in a first time period;
a time period determination module for determining a second time period relative to the first time period;
the second pushing index counting module is used for acquiring a second pushing index for pushing the candidate video file in the second time period;
the alarm information generation module is used for generating alarm information if the difference value between the first pushing index and the second pushing index is larger than a preset index threshold value;
the time period determination module includes:
the first period determining submodule is used for determining a first period in which the first time period is positioned;
the interval determining submodule is used for determining the interval of the first time period in the first period;
a second period determining submodule for determining a second period located before the first period;
the interval setting submodule is used for setting the period in the interval in the second period as a second time period; or, a period determining submodule, configured to determine a period in which the first time period is located;
the time period setting submodule is used for setting the time period before the first time period as a second time period in the period;
the feedback operation data counting module is used for counting the feedback operation data of the first client to the candidate video file;
the candidate video file transfer module is used for transferring at least part of the candidate video files to a preset second video pool according to the feedback operation data;
a target video file selection module, configured to select at least a portion of the candidate video files from the second video pool as target video files;
and the target video file pushing module is used for pushing the target video file to a second client side for displaying.
17. A computer device, characterized in that the computer device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the video push method of any of claims 1-15.
18. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the video push method according to any one of claims 1 to 15.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911051675.8A CN110769283B (en) | 2019-10-31 | 2019-10-31 | Video pushing method and device, computer equipment and storage medium |
PCT/CN2020/107976 WO2021082603A1 (en) | 2019-10-31 | 2020-08-07 | Video pushing method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911051675.8A CN110769283B (en) | 2019-10-31 | 2019-10-31 | Video pushing method and device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110769283A CN110769283A (en) | 2020-02-07 |
CN110769283B true CN110769283B (en) | 2021-08-27 |
Family
ID=69334940
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911051675.8A Active CN110769283B (en) | 2019-10-31 | 2019-10-31 | Video pushing method and device, computer equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110769283B (en) |
WO (1) | WO2021082603A1 (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110769283B (en) * | 2019-10-31 | 2021-08-27 | 广州市网星信息技术有限公司 | Video pushing method and device, computer equipment and storage medium |
CN111464864B (en) * | 2020-04-02 | 2022-12-06 | Oppo广东移动通信有限公司 | Reverse order video acquisition method and device, electronic equipment and storage medium |
CN111726649B (en) * | 2020-06-28 | 2021-12-28 | 百度在线网络技术(北京)有限公司 | Video stream processing method, device, computer equipment and medium |
CN112579822A (en) * | 2020-12-25 | 2021-03-30 | 百果园技术(新加坡)有限公司 | Video data pushing method and device, computer equipment and storage medium |
CN112788702B (en) * | 2021-01-07 | 2022-07-22 | 西安电子科技大学 | Mapping table item cache updating method for satellite Internet of things mobile terminal |
CN112836085A (en) * | 2021-02-08 | 2021-05-25 | 深圳市欢太科技有限公司 | Weight adjusting method and device and storage medium |
CN113722615B (en) * | 2021-08-19 | 2023-11-21 | 北京智慧星光信息技术有限公司 | Accurate pushing method and system for internet data, electronic equipment and storage medium |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9465435B1 (en) * | 2013-08-26 | 2016-10-11 | Google Inc. | Segmentation of a video based on user engagement in respective segments of the video |
CN106294775A (en) * | 2016-08-11 | 2017-01-04 | 合智能科技(深圳)有限公司 | Content delivery method and device |
CN107526758B (en) * | 2016-10-25 | 2020-07-28 | 腾讯科技(深圳)有限公司 | Message pushing method and device |
CN106779985A (en) * | 2017-02-24 | 2017-05-31 | 武汉奇米网络科技有限公司 | A kind of method and system of personalized commercial sequence |
US10635707B2 (en) * | 2017-09-07 | 2020-04-28 | Xerox Corporation | Contextual memory bandit for proactive dialogs |
CN107592572B (en) * | 2017-09-21 | 2021-05-14 | 广州方硅信息技术有限公司 | Video recommendation method, device and equipment |
CN110413895B (en) * | 2019-07-31 | 2024-07-09 | 腾讯科技(深圳)有限公司 | Information pushing method and related device |
CN110809177B (en) * | 2019-10-22 | 2021-11-05 | 腾讯科技(深圳)有限公司 | Content processing method, content processing device, server and storage medium |
CN110769283B (en) * | 2019-10-31 | 2021-08-27 | 广州市网星信息技术有限公司 | Video pushing method and device, computer equipment and storage medium |
-
2019
- 2019-10-31 CN CN201911051675.8A patent/CN110769283B/en active Active
-
2020
- 2020-08-07 WO PCT/CN2020/107976 patent/WO2021082603A1/en active Application Filing
Also Published As
Publication number | Publication date |
---|---|
WO2021082603A1 (en) | 2021-05-06 |
CN110769283A (en) | 2020-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110769283B (en) | Video pushing method and device, computer equipment and storage medium | |
EP2479684B1 (en) | Method and evaluation server for evaluating a plurality of videos | |
US10664872B2 (en) | Systems and methods for generating network intelligence through real-time analytics | |
CN105163142B (en) | A kind of user preference determines method, video recommendation method and system | |
CN103634687B (en) | The method and system of video search result are provided in intelligent television | |
CN104853230B (en) | A kind of hot video method for pushing and device | |
CN109582903B (en) | Information display method, device, equipment and storage medium | |
CN103763585A (en) | User characteristic information obtaining method and device and terminal device | |
CN105376649B (en) | Realize the blind operating method of the set-top box of accurate combined recommendation and system | |
CN104079999A (en) | Video screenshot preview method and system used on smart television | |
US20170169062A1 (en) | Method and electronic device for recommending video | |
CN109462765B (en) | Method and device for issuing and displaying recommended page | |
WO2018019210A1 (en) | Method and device for monitoring user status of internet protocol television (iptv) | |
CN106844532B (en) | Application program acquisition method and device and terminal equipment | |
CN105843876A (en) | Multimedia resource quality assessment method and apparatus | |
US20090157670A1 (en) | Contents-retrieving apparatus and method | |
CN106534984A (en) | TV program pushing method and device | |
CN112995765A (en) | Network resource display method and device | |
CN107509088A (en) | A kind of collection of drama renewal reminding method, terminal and computer-readable recording medium | |
CN105763947A (en) | Method for extracting features and interests of smart television users | |
CN110874639A (en) | Method and device for acquiring operation information | |
CN109271580B (en) | Search method, device, client and search engine | |
CN110248198B (en) | Media information aggregation method, device and system | |
CN111104582A (en) | Fault-tolerant method and device for search page and electronic equipment | |
JP4224707B2 (en) | Information classification analysis system, information classification analysis and program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |